基于卷积神经网络的笑脸识别

一、环境配置

安装TensorFlow和Keras库
anaconda命令行中输入以下指令：
conda install tensorflow
conda install keras

二、编码

1.训练数据集

1.导入Keras

import keras
keras.__version__

2.读取数据集，训练

import os, shutil

# The path to the directory where the original
# dataset was uncompressed
riginal_dataset_dir = 'F:\\Anaconda3\\project\\jupyter\\genki4k'

# The directory where we will
# store our smaller dataset
base_dir = 'F:\\Anaconda3\\project\\jupyter\\genki4k\\smile_and_unsmile'
os.mkdir(base_dir)

# Directories for our training,
# validation and test splits
train_dir = os.path.join(base_dir, 'train')
os.mkdir(train_dir)
validation_dir = os.path.join(base_dir, 'validation')
os.mkdir(validation_dir)
test_dir = os.path.join(base_dir, 'test')
os.mkdir(test_dir)

# Directory with our training smile pictures
train_smile_dir = os.path.join(train_dir, 'smile')
os.mkdir(train_smile_dir)

# Directory with our training unsmile pictures
train_unsmile_dir = os.path.join(train_dir, 'unsmile')
os.mkdir(train_unsmile_dir)

# Directory with our validation smile pictures
validation_smile_dir = os.path.join(validation_dir, 'smile')
os.mkdir(validation_smile_dir)

# Directory with our validation unsmile pictures
validation_unsmile_dir = os.path.join(validation_dir, 'unsmile')
os.mkdir(validation_unsmile_dir)

# Directory with our validation smile pictures
test_smile_dir = os.path.join(test_dir, 'smile')
os.mkdir(test_smile_dir)

# Directory with our validation unsmile pictures
test_unsmile_dir = os.path.join(test_dir, 'unsmile')
os.mkdir(test_unsmile_dir)

3.打印数据集中笑脸和非笑脸图片数

print('total training smile images:', len(os.listdir(train_smile_dir)))
print('total training unsmile images:', len(os.listdir(train_unsmile_dir)))
print('total validation smile images:', len(os.listdir(validation_smile_dir)))
print('total validation unsmile images:', len(os.listdir(validation_unsmile_dir)))
print('total test smile images:', len(os.listdir(test_smile_dir)))
print('total test unsmile images:', len(os.listdir(test_unsmile_dir)))

4.构建小型卷积神经网络

from keras import layers
from keras import models

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

from keras import optimizers

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc'])

5.数据预处理

from keras.preprocessing.image import ImageDataGenerator

# All images will be rescaled by 1./255
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary')

for data_batch, labels_batch in train_generator:
    print('data batch shape:', data_batch.shape)
    print('labels batch shape:', labels_batch.shape)
    break

6.训练模型

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=30,
      validation_data=validation_generator,
      validation_steps=50)

%matplotlib inline
import matplotlib.pyplot as plt

acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()

plt.show()

7.数据增强

datagen = ImageDataGenerator(
      rotation_range=40,
      width_shift_range=0.2,
      height_shift_range=0.2,
      shear_range=0.2,
      zoom_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

# This is module with image preprocessing utilities
from keras.preprocessing import image

fnames = [os.path.join(train_smile_dir, fname) for fname in os.listdir(train_smile_dir)]

# We pick one image to "augment"
img_path = fnames[3]

# Read the image and resize it
img = image.load_img(img_path, target_size=(150, 150))

# Convert it to a Numpy array with shape (150, 150, 3)
x = image.img_to_array(img)

# Reshape it to (1, 150, 150, 3)
x = x.reshape((1,) + x.shape)

# The .flow() command below generates batches of randomly transformed images.
# It will loop indefinitely, so we need to `break` the loop at some point!
i = 0
for batch in datagen.flow(x, batch_size=1):
    plt.figure(i)
    imgplot = plt.imshow(image.array_to_img(batch[0]))
    i += 1
    if i % 4 == 0:
        break

plt.show()

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dropout(0.5))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc'])

train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=40,
    width_shift_range=0.2,
    height_shift_range=0.2,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,)

# Note that the validation data should not be augmented!
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=32,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50)

model.save('smile_and_unsmile_2.h5')

acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()

2.摄像头实时笑脸识别

import cv2
from keras.preprocessing import image
from keras.models import load_model
import numpy as np
import dlib
from PIL import Image
model = load_model('smile_and_unsmile_2.h5')
detector = dlib.get_frontal_face_detector()
video=cv2.VideoCapture(0)
font = cv2.FONT_HERSHEY_SIMPLEX
def rec(img):
    gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    dets=detector(gray,1)
    if dets is not None:
        for face in dets:
            left=face.left()
            top=face.top()
            right=face.right()
            bottom=face.bottom()
            cv2.rectangle(img,(left,top),(right,bottom),(0,255,0),2)
            img1=cv2.resize(img[top:bottom,left:right],dsize=(150,150))
            img1=cv2.cvtColor(img1,cv2.COLOR_BGR2RGB)
            img1 = np.array(img1)/255.
            img_tensor = img1.reshape(-1,150,150,3)
            prediction =model.predict(img_tensor)    
            print(prediction)
            if prediction[0][0]>0.5:
                result='unsmile'
            else:
                result='smile'
            cv2.putText(img, result, (left,top), font, 2, (0, 255, 0), 2, cv2.LINE_AA)
        cv2.imshow('Video', img)
while video.isOpened():
    res, img_rd = video.read()
    if not res:
        break
    rec(img_rd)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
video.release()
cv2.destroyAllWindows()

运行结果如下：